Security audit
adversarial-coach
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain Markdown review checklist for adversarial implementation review and does not include hidden execution, persistence, or unrelated data access.
Before installing, understand that this skill is intended to make the agent act as a strict code reviewer and may prompt it to read requirements, inspect code, and run tests. That behavior fits the skill's purpose, and no hidden or privileged behavior was found in the inspected artifact.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.